Paper: arXiv 2405.15833
Authors: Jianyuan Zhong, Zhijian Xu, Saizhuo Wang, Xiangyu Wen, Jian Guo, Qiang Xu
Abstract
In quantitative investment, constructing characteristic-sorted portfolios is a crucial strategy for asset allocation. Traditional methods transform raw stock data of varying frequencies into predictive characteristic factors for asset sorting, often requiring extensive manual design and misalignment between prediction and optimization goals. To address these challenges, we introduce Direct Sorted Portfolio Optimization (DSPO), an innovative end-to-end framework that efficiently processes raw stock data to construct sorted portfolios directly. DSPO’s neural network architecture seamlessly transitions stock data from input to output while effectively modeling the intra-dependency of time-steps and inter-dependency among all tradable stocks. Additionally, we incorporate a novel Monotonical Logistic Regression loss, which directly maximizes the likelihood of constructing optimal sorted portfolios. To the best of our knowledge, DSPO is the first method capable of handling market cross-sections with thousands of tradable stocks fully end-to-end from raw multi-frequency data. Empirical results demonstrate DSPO’s effectiveness, yielding a RankIC of 10.12% and an accumulated return of 121.94% on the New York Stock Exchange in 2023-2024, and a RankIC of 9.11% with a return of 108.74% in other markets during 2021-2022.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper presents advanced neural network architectures (Transformers, CNNs) and a novel Monotonical Logistic Regression loss, indicating high mathematical sophistication. The empirical evaluation is strong, featuring backtest results with specific metrics (RankIC, accumulated returns) across major markets (NYSE, A-Share) and ablation studies, demonstrating significant implementation and data validation.
Research Flowchart
flowchart TD Start["Research Goal<br>Construct sorted portfolios directly from raw stock data"] --> Input["Raw Multi-Frequency Data<br>NYSE (2023-2024) & Other Markets (2021-2022)"] Input --> Method["Methodology: DSPO Framework<br>End-to-End Neural Network Architecture"] Method --> Process["Computational Process<br>1. Intra-dependency (Time-steps)<br>2. Inter-dependency (Cross-section)<br>3. Monotonical Logistic Regression Loss"] Process --> Outcome["Key Findings & Outcomes<br>RankIC: 10.12% | Return: 121.94% (NYSE)<br>RankIC: 9.11% | Return: 108.74% (Others)"] style Start fill:#f9f,stroke:#333,stroke-width:2px style Input fill:#ccf,stroke:#333,stroke-width:2px style Method fill:#cfc,stroke:#333,stroke-width:2px style Process fill:#cff,stroke:#333,stroke-width:2px style Outcome fill:#ffc,stroke:#333,stroke-width:2px
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes Direct Sorted Portfolio Optimization (DSPO), an end‑to‑end neural framework that directly constructs characteristic‑sorted portfolios from raw multi‑frequency stock data.
Source sentence
we introduce Direct Sorted Portfolio Optimization (DSPO), an innovative end-to-end framework that efficiently processes raw stock data to construct sorted portfolios directly.
Assumes 4
- High‑frequency and low‑frequency data are available for all actively traded stocks. data
Source sentence
and obtained A‑Share data through professional contacts. Both datasets include high‑frequency trading signals
- Transaction costs are fixed at 0.02% per side with specified volume limits and price impacts. execution
Source sentence
... adjusted for commission fees and slippage rates set at 0.0002 (USD or CNY) and with volume limits and price impacts of 0.0025 and 0.01, respectively.
- Cross‑sectional sub‑sampling yields enough training samples to avoid over‑fitting. model
Source sentence
To address this, we propose an Cross‑Section Sub‑Sampling Strategy. We randomly select m distinct trading days
- The ranking loss (Monotonical Logistic Regression) approximates the likelihood of correct sorted portfolios. model
Source sentence
To enhance optimization and numerical stability, while minimizing the negative log‑likelihood (logistic loss), we employ the hyperbolic tangent function (tanh) as a smoother alternative to the sign function.
Data
2023 – 2024 · New York Stock Exchange · equities · intraday
- NYSE raw data market-prices commercial
Source sentence
For the New York Stock Exchange (NYSE), we utilize transaction data spanning 2020 to 2022 for model training, with evaluations conducted in 2023 ...
- A‑Share raw data fundamentals proprietary
Source sentence
In the case of the A‑Share market, training is performed using data from 2018 to 2020, followed by direct deployment in 2021.
Costs
Modeled
Commission fees and slippage set at 0.0002 per side; volume limits 0.0025 and price impact 0.01.
Source sentence
... adjusted for commission fees and slippage rates set at 0.0002 (USD or CNY) and with volume limits and price impacts of 0.0025 and 0.01, respectively.
Finds 2
total return 121.9%
- DSPO achieves a RankIC of 10.12% and an accumulated return of 121.94% on NYSE data (2023‑2024). performance
Source sentence
Empirical results demonstrate DSPO's effectiveness, yielding a RankIC of 10.12% and an accumulated return of 121.94% on the New York Stock Exchange in 2023‑2024
- On other markets (2021‑2022) DSPO attains a RankIC of 9.11% with a return of 108.74%. performance
Source sentence
and a RankIC of 9.11% with a return of 108.74% in other markets during 2021‑2022.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 17 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (86)
- Are transformers effective for time series forecasting? (2023)
- Alphastock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks (2019)
- 101 Formulaic Alphas (2016) — link
- DeepTrader : A Deep Reinforcement Learning Approach for Risk - Return Balanced Portfolio Management with Market Conditions Embedding (2021) — link
- Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting (2020) — link
- Stock Selection via Spatiotemporal Hypergraph Attention Network : A Learning to Rank Approach (2021) — link
- PRUDEX - Compass : Towards Systematic Evaluation of Reinforcement Learning in Financial Markets — → 2302.00586
- TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning (2023) — link
and 78 more
- A Survey of Forex and Stock Price Prediction Using Deep Learning (2021) — link
- Smart “ Predict , then Optimize ” (2022) — link
- Wavenet: A generative model for raw audio (2016) — link
- Neural discrete representation learning (2017)
- Research on Stock Price Prediction Method Based on Convolutional Neural Network (2019) — link
- Conditional image generation with pixelcnn decoders (2016)
- A time series is worth 64 words: Long-term forecasting with transformers (2022) — link
- Characteristic-sorted portfolios: Estimation and inference (2020)
- Synergistic Formulaic Alpha Generation for Quantitative Trading based on Reinforcement Learning (2024) — link
- Deep Inception Networks: A General End-to-End Framework for Multi-asset Quantitative Strategies — → 2307.05522
- Synergistic Formulaic Alpha Generation for Quantitative Trading based on Reinforcement Learning (2024) — link
- Training language models to follow instructions with human feedback (2022)
- Direct preference optimization: Your language model is secretly a reward model (2024)
- Performance of High -frequency Volume -price Factors in Stocks and Futures (2018) — link
- Reference-free monolithic preference optimization with odds ratio (2024) — link
- Online learning: A comprehensive survey (2021)
- Deep residual learning for image recognition (2016)
- Attention is all you need (2017)
- Reasonnet: End-to-end driving with temporal and global reasoning (2023)
- Robust speech recognition via large-scale weak supervision (2023)
- Neural machine translation by jointly learning to align and translate (2014) — link
- Advancing Multimodal Medical Capabilities of Gemini (2024) — link
- End-to-end robotic reinforcement learning without reward engineering (2019) — link
- Temporal relational ranking for stock prediction (2019)
- StockFormer: Learning Hybrid Trading Machines with Predictive Coding (2023) — link
- A network-based end-to-end trainable task-oriented dialogue system (2016) — link
- Action-based conversations dataset: A corpus for building more in-depth task-oriented dialogue systems (2021) — link
- Dialogue act modeling for automatic tagging and recognition of conversational speech (2000)
- The second dialog state tracking challenge (2014)
- Models of natural language understanding. (1995)
- Commonsense reasoning for natural language understanding: A survey of benchmarks, resources, and approaches (2019) — link
- Scalable multi-domain dialogue state tracking (2017)
- Towards universal dialogue state tracking (2018)
- Toward scalable neural dialogue state tracking model (2018) — link
- Neural belief tracker: Data-driven dialogue state tracking (2016) — link
- Survey of the state of the art in natural language generation: Core tasks, applications and evaluation (2018)
- Survey of hallucination in natural language generation (2023)
- Dialogue state tracking with a language model using schema-driven prompting (2021) — link
- Competitive Markov decision processes (2012)
- Markov decision processes (2013)
- Factors affecting text mining based stock prediction: Text feature representations, machine learning models, and news platforms (2022)
- Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process (2022)
- A multi-feature stock price prediction model based on multi-feature calculation, LASSO feature selection, and Ca-LSTM network (2022)
- Predicting earnings per share using feature-engineered Extreme Gradient Boosting (XGBoost) models (2022)
- AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment (2020)
- Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment — → 2308.00016
- Mining profitable alpha factors via convolution kernel learning (2023)
- Enhancing Stock Movement Prediction with Adversarial Training (2019) — link
- Mtmd: multi-scale temporal memory learning and efficient debiasing framework for stock trend forecasting (2022) — link
- Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts (2021) — link
- DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting — → 2306.09862
- An ensemble of LSTM neural networks for high-frequency stock market classification (2019)
- Deep learning with long short-term memory networks for financial market predictions (2018)
- A deep learning approach for the Netflix prize (2012) — link
- Listwise approach for learning to rank with ranknet (2013)
- Prediction of Stock Prices using Machine Learning (Regression, Classification) Algorithms (2020) — link
- AutoInt: Automatic feature interaction learning via self-attentive neural networks (2015) — link
- Deep learning for information retrieval (2015)
- Position-Aware Factorization Machines for Personalized Recommendation (2016)
- Bilateral multi-perspective matching for natural language sentences (2017)
- Deep ranking using pairwise tensor factorization (2015)
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (2024)
- Fake Alignment: Are LLMs Really Aligned Well? (2023)
- Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents (2023)
- PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety (2024)
- Universal and Transferable Adversarial Attacks on Aligned Language Models (2023)
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass Safety Filters of Text-to-Image Models (2024) — link
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs (2023) — link
- MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use (2023)
- Evil Geniuses: Delving into the Safety of LLM-based Agents (2023)
- Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents (2024)
- ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages (0)
- RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (0)
- WIPI:s A New Web Threat for LLM-Driven Web Agents (2024) — link
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving (2023)
- MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning (2023)
- Solving Challenging Math Word Problems Using GPT -4 Code Interpreter with Code-based Self-Verification (2024) — link
- Measuring Mathematical Problem Solving With the MATH Dataset (2021)
4 of 86 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.